VERSIL91 commited on
Commit
c5bedc3
·
verified ·
1 Parent(s): 71e279a

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:000fd5bb40bcefbd719d578959703d6d501c145e300f20f3d01460eea20abbf3
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892b2d42198993db5ab0e3fc87f2fffbb65db2c4e57ccdf362942b8c8eeb1044
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b0854de301628aad96a858f18d1be4ddca94970e06ab003d40cb24bb65a8557
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f23d3f96c11941e5df880fb82a6b54111e233bd714cbc64108145fed4c197ae
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4433eec61889554671284f5fe3d196c7c49114953d9ff8c6a36826f95d9a19bf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51885bfa808d7dd91dfb7a6d29e9430a88ce71253079a7b02ced5e7584658c6b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.01606425702811245,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 27.716,
38
  "eval_steps_per_second": 13.858,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1873061628346368.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0321285140562249,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 27.716,
38
  "eval_steps_per_second": 13.858,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.024096385542168676,
43
+ "grad_norm": 2.448141098022461,
44
+ "learning_rate": 3e-05,
45
+ "loss": 23.0411,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0321285140562249,
50
+ "grad_norm": 1.915059208869934,
51
+ "learning_rate": 4e-05,
52
+ "loss": 25.1573,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0321285140562249,
57
+ "eval_loss": 1.5223687887191772,
58
+ "eval_runtime": 7.6013,
59
+ "eval_samples_per_second": 27.627,
60
+ "eval_steps_per_second": 13.813,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3868279449845760.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null